We propose a joint covert beamforming design and jamming strategy to protect the communication process between Alice and Bob from being discovered by Willie with the help of another pair of neutral nodes. Specifically...
详细信息
Machine Learning (ML) with 5G technology has revolutionized smart healthcare. It has helped improve the quality of care, such as real-time analysis, decision-making, patient monitoring, and personalized treatments. In...
详细信息
In response to the problem of traditional methods ignoring audio modality tampering, this study aims to explore an effective deep forgery video detection technique that improves detection precision and reliability by ...
详细信息
In response to the problem of traditional methods ignoring audio modality tampering, this study aims to explore an effective deep forgery video detection technique that improves detection precision and reliability by fusing lip images and audio signals. The main method used is lip-audio matching detection technology based on the Siamese neural network, combined with MFCC (Mel Frequency Cepstrum Coefficient) feature extraction of band-pass filters, an improved dual-branch Siamese network structure, and a two-stream network structure design. Firstly, the video stream is preprocessed to extract lip images, and the audio stream is preprocessed to extract MFCC features. Then, these features are processed separately through the two branches of the Siamese network. Finally, the model is trained and optimized through fully connected layers and loss functions. The experimental results show that the testing accuracy of the model in this study on the LRW (Lip Reading in the Wild) dataset reaches 92.3%;the recall rate is 94.3%;the F1 score is 93.3%, significantly better than the results of CNN (Convolutional Neural networks) and LSTM (Long Short-Term Memory) models. In the validation of multi-resolution image streams, the highest accuracy of dual-resolution image streams reaches 94%. Band-pass filters can effectively improve the signal-to-noise ratio of deep forgery video detection when processing different types of audio signals. The real-time processing performance of the model is also excellent, and it achieves an average score of up to 5 in user research. These data demonstrate that the method proposed in this study can effectively fuse visual and audio information in deep forgery video detection, accurately identify inconsistencies between video and audio, and thus verify the effectiveness of lip-audio modality fusion technology in improving detection performance.
IoT involves sensors for monitoring and wireless networks for efficient communication. However, resource-constrained IoT devices and limitations in existing wireless technologies hinder its full potential. Integrating...
详细信息
Urban traffic congestion poses a major challenge, particularly for emergency services like ambulances, where delays can have life-threatening consequences. This paper proposes a novel, cost-efficient Automated Traffic...
详细信息
ISBN:
(数字)9798331527518
ISBN:
(纸本)9798331527525
Urban traffic congestion poses a major challenge, particularly for emergency services like ambulances, where delays can have life-threatening consequences. This paper proposes a novel, cost-efficient Automated Traffic Light Control System aimed at prioritizing ambulances at busy intersections, thereby reducing delays and ensuring faster response times. The system utilizes Raspberry Pi Zero 2W, Laser Diodes (KY-008), and Light Dependent Resistors (LDRs) to detect ambulances and dynamically control traffic lights. Unlike traditional systems relying on GPS or RFID technologies, this laser-based approach offers greater precision and affordability through the use of modulated laser signals. Experimental results reveal that this system reduces ambulance response times by 35%. The tests were conducted under simulated urban conditions, highlighting the system's capability to outperform conventional solutions. The simplicity of integration and real-time responsiveness underscore its potential for widespread urban adoption.
The control of heliostats in existing Concentrated Solar Power (CSP) fields is performed based on wired communications, resulting in high installation, maintenance, and operation cost. This paper introduces a wireless...
详细信息
Though extensive research efforts have been devoted to the problem of computing resource pricing, they mainly focus on single computing paradigms. In this paper, we provide a holistic approach to this problem, by trea...
详细信息
This study introduces a deep learning-based method for classifying brain tumors using a pre-trained VGG19 convolutional neural network (CNN). By leveraging transfer learning, we adapted the VGG19 model with custom ful...
详细信息
ISBN:
(数字)9798331527518
ISBN:
(纸本)9798331527525
This study introduces a deep learning-based method for classifying brain tumors using a pre-trained VGG19 convolutional neural network (CNN). By leveraging transfer learning, we adapted the VGG19 model with custom fully connected layers and trained it on MRI images to differentiate between tumor and non-tumor cases. The model’s architecture includes dropout layers to minimize overfitting and enhance generalization while maintaining the robust feature extraction capabilities of the VGG19 base. We developed a Flask web application interface to make the model accessible via web-based user input, allowing users to upload MRI images and receive immediate predictions on tumor presence. Preliminary results show that proposed model can accurately classify brain tumor images with high accuracy, highlighting the potential of deep learning in automating brain tumor diagnostics. This tool could significantly aid clinicians in making rapid and accurate diagnoses, ultimately improving patient outcomes.
Intent-Driven networks (IDNs) are designed to improve network management efficiency by transforming high-level intents into actionable configurations. Due to evolving user requirements and network dynamics, a semantic...
详细信息
To overcome the limited endurance of traditional unmanned aerial vehicles (UAVs), we propose a network of robotic aerial base stations (RABSs) that can energy-efficiently anchor into tall urban landforms, such as lamp...
详细信息
ISBN:
(数字)9798350368369
ISBN:
(纸本)9798350368376
To overcome the limited endurance of traditional unmanned aerial vehicles (UAVs), we propose a network of robotic aerial base stations (RABSs) that can energy-efficiently anchor into tall urban landforms, such as lampposts. This approach enables the creation of a hyper-flexible wireless multi-hop network, designed to support green, densified, and dynamic network requirements, thereby ensuring reliable long-term coverage for the whole observed region. The proposed network infrastructure can concurrently address the backhaul link capacity bottleneck and support access link traffic demand in the millimeter-wave (mmWave) frequency band. Specifically, the RABSs grasping locations, resource blocks (RBs) assignment, and route flow control are simultaneously optimized to maximize the served traffic demands. The group of RABSs capitalizes on the fact that traffic distribution varies considerably across both time and space within a given geographical area. Hence, they are able to relocate to suitable locations, i.e., ‘follow’ the traffic demand as it unfolds to increase the overall network efficiency. To tackle the curse of dimensionality of the proposed mixed-integer problem, we propose a greedy algorithm to obtain a competitive solution with low computational complexity. A wide set of numerical investigations reveals that RABSs could improve the served traffic demand. For instance, compared to networks with randomly deployed fixed small cells, the proposed mode serves at most 65% more traffic demand.
暂无评论